Polly
Multi-agent coding orchestrator. Polly breaks your task into sub-tasks and delegates each one to a different AI agent, with cross-vendor code review built in.
omni polly
omni # also launches Polly (it's the default)How it works
Polly is a supervisor that never writes code itself. It decomposes your goal into sub-tasks and delegates each one to a sub-agent running on its own harness and git worktree. One agent implements, a different agent reviews. Each implementer opens its own PR. Polly never merges. The human decides.
| Sub-agent | Harness | Role |
|---|---|---|
claude_code | claude-native | Claude Code |
codex | codex-native | Codex |
pi | pi | Pi (headless, any gateway model) |
Skills
/fanoutruns independent tasks in parallel. Each gets its own git worktree and sub-agent. Each opens its own PR./cross-reviewsends an implementer's diff to a different-vendor reviewer. Blocking issues loop back as fixes until clean./investigatedelegates read-only work (debugging, audits, code understanding) to sub-agents and synthesizes findings.
When to use
- Large refactors that benefit from parallel work.
- Cross-vendor code review where one agent writes and another reviews.
- Specialized sub-tasks routed to the harness best suited for them.